Check patentability & draft patents in minutes with Patsnap Eureka AI!

A Feature Attachment Code Smell Detection Method Based on Deep Learning

A technology of deep learning and detection methods, applied in the direction of neural learning methods, code reconstruction, instruments, etc., to achieve the effect of increasing the average recall rate and improving the average accuracy rate

Inactive Publication Date: 2019-02-26
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, empirical studies have shown that this statistical machine learning-based approach to odor detection has key limitations that warrant further study

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Feature Attachment Code Smell Detection Method Based on Deep Learning
  • A Feature Attachment Code Smell Detection Method Based on Deep Learning
  • A Feature Attachment Code Smell Detection Method Based on Deep Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0035] This embodiment elaborates in detail the method and effect when the detection method of the present invention is implemented under 7 open source projects.

[0036] Under the hardware environment shown in Table 1, the open source software shown in Table 2 is trained and predicted.

[0037] Table 1: Hardware environment configuration information table

[0038]

[0039] Table 2: Basic information table of open source software

[0040] Number of open source projects

writing language

Item size (LOC)

Average item size (LOC)

7

Java

11,734～444,493

139,742

[0041] From the 7 open source Java projects, the data of one of the open source projects is used as the test data, and the data of the other 6 open source projects are used as the training data.

[0042] A feature-attachment code smell detection method based on deep learning, such as figure 1 shown, including the following steps:

[0043]Step 1: Extract the movable method info...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a feature-attachment code odor detection method based on deep learning, which belongs to the technical field of computer software. First extract the movable method information and distance of the open source software used for training, generate a training set, convert the extracted movable method information and distance into training data represented by word vectors, and input the training data into the convolutional neural network to train the neural network Model. Then, the method information and distance of the movable method of the open source software used for testing are extracted, a test data set is generated, and all the data in the test data set are converted into the data to be tested represented by word vectors. Input the data to be tested into the neural network model, and the model will automatically output 0 or 1, where 1 represents the presence of feature attachment code smell, and 0 represents the absence of it. Compared with the existing detection method, the detection method of the present invention greatly improves the average recall rate and improves the average accuracy rate at the same time.

Description

technical field [0001] The invention relates to a code odor detection method aimed at feature attachment, and belongs to the technical field of computer software. Background technique [0002] Code Refactoring refers to improving the internal structure of a software system without changing its external behavior. Code refactoring can improve the quality and performance of the software by adjusting the program code, make the design pattern and structure of the program more reasonable, and improve the scalability and maintainability of the software. Code refactoring is a methodical approach to program organization that has been honed over time to minimize the probability of errors being introduced during the organization process. Essentially, code refactoring is about improving the design of the code after it is written. Software refactoring is widely used to improve software quality by refactoring each of its structures while keeping its external behavior unchanged. Most ex...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F8/72G06K9/62G06N3/08
CPCG06F8/72G06N3/08G06F18/2411G06F18/214
Inventor 刘辉许志凤
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com